On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “SATNet”

Techniques for Symbol Grounding with SATNetcs.AI

SATNet solves the Symbol Grounding Problem, enabling self-supervised learning.

problem Mapping visual inputs to symbolic variables without explicit supervision.

method Self-supervised pre-training pipeline and proofreading method.

result SATNet achieves full accuracy with no label leakage, surpassing state-of-the-art.

SATNet Symbol Grounding Problem Neurosymbolic Systems Self-supervised Learning Visual Sudoku

2021-06-16abs ↗pdf ↗

SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercs.LG

Integrating logical reasoning within deep learning architectures has been a major goal of modern AI systems. In this paper, we propose a new direction toward this goal by introducing a differentiable (smoothed) maximum satisfiability (MAXSAT) solver that can be integrated into the loop of larger deep learning systems. …

2019-05-29abs ↗pdf ↗